Search Results for "high performance computing"

...The system operates in a ReAct-style loop where the agent profiles baseline implementations, writes CUDA code, compiles it in a sandbox, and iteratively refines performance. CUDA-Agent has demonstrated strong benchmark results, achieving high pass rates and significant speedups compared with compiler baselines such as torch.compile.

holaOSc is an AI-native operating system concept designed to integrate intelligent agents directly into the core of the computing environment. It provides a framework where AI agents manage tasks, workflows, and interactions across applications. The system emphasizes seamless automation, allowing users to interact with their computer through natural language and high-level instructions. It integrates memory, context awareness, and task orchestration into a unified environment. ...

AutoAgent is an experimental AI framework focused on autonomous agent engineering, where a meta-agent iteratively improves another agent’s architecture without direct human intervention. Instead of manually tuning prompts or workflows, developers define high-level goals in a configuration file, and the system continuously modifies its own tools, orchestration, and logic based on benchmark performance. It operates through a loop of testing, analyzing failures, and refining the agent’s configuration to maximize a scoring metric. The framework uses a single-file agent harness combined with structured tasks and evaluation suites to guide optimization. ...

...It offers features such as agents that can converse with other agents, LLM and tool use support, autonomous and human-in-the-loop workflows, and multi-agent conversation patterns. AutoGen provides multi-agent conversation framework as a high-level abstraction. With this framework, one can conveniently build LLM workflows. AutoGen offers a collection of working systems spanning a wide range of applications from various domains and complexities. AutoGen supports enhanced LLM inference APIs, which can be used to improve inference performance and reduce cost.

SCASTD (Statistical Casting Daemon) is a lightweight, high-performance statistics collection and analytics engine we designed specifically for streaming media infrastructure. Unlike traditional streaming servers, we built SCASTD to be the definitive monitoring solution that bridges legacy and modern streaming protocols, providing unified analytics across your entire streaming ecosystem